Semiempirical Neural Network Models of Controlled Dynamical Systems

Tiumentsev, Yury V.; Egorchev, Mikhail V.

doi:10.1016/b978-0-12-815254-6.00015-0

Cited by 2 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A NN generally comprises the input layer, a few hidden layers, and the output layer. These layers are connected through neurons; each layer's output becomes the next layer's input [36,38].…”

Section: Neural Network-based Wind Speed Estimationmentioning

confidence: 99%

“…The training algorithm used is the Levenberg-Marquardt method, which iteratively adjusts the weights and biases of the network to minimize the root mean square error (RMSE) performance function. The activation function is the rectified linear unit (ReLU) [36][37][38][39].…”

Section: Neural Network-based Wind Speed Estimationmentioning

confidence: 99%

“…The nonlinear estimators such as extended Kalman filters have been utilised [32][33][34][35] but the design of such estimators requires accurate models, which are often unavailable. As a result, NNs have been gaining more attention for designing nonlinear wind speed estimators [36][37][38][39]. Neural networks (NNs) are used to predict wind speed instead of real-time adaptive control methods because NNs capture complex patterns and nonlinear relationships in data.…”

Section: Introductionmentioning

confidence: 99%

“…The wind speed estimation method introduced here is also based on a NN but differs from the ones in the literature [36][37][38][39]. It focuses on being cost-effective in addition to providing an accurate wind speed estimation.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Predictive Control of a Wind Turbine Based on Neural Network-Based Wind Speed Estimation

2023

View full text Add to dashboard Cite

Predictive control is an advanced control technique that performs well in various application domains. In this work, linearised control design models are first derived in state-space form from the full nonlinear model of the 5 MW Supergen (Sustainable Power Generation and Supply) exemplar wind turbine. Feedback model predictive controllers (FB-MPCs) and feedforward model predictive controllers (FF-MPCs) are subsequently designed based on these linearised models. A neural network (NN)-based wind speed estimation method is then employed to obtain the accurate wind estimation required for designing a FF-MPC. This method uses a LiDAR to be shared between multiple wind turbines in a cluster, i.e., one turbine is mounted with a LiDAR, and each of the remaining turbines from the cluster is provided with a NN-based estimator, which replaces the LiDAR, making the approach more economically viable. The resulting controllers are tested by application to the full nonlinear model (based on which the linearised models are derived). Moreover, the mismatch between the control design model and the simulation model (model–plant mismatch) allows the robustness of the controllers’ design to be tested. Simulations are carried out at varying wind speeds to evaluate the robustness of the controllers by applying them to a full nonlinear 5 MW Matlab/SIMULINK model of the same exemplar Supergen wind turbine. Improved torque/speed plane tracking is achieved with a FF-MPC compared to a FB-MPC. Simulation results further demonstrate that the control performance is enhanced in both the time and frequency domains without increasing the wind turbine’s control activity; that is, the controller’s gain crossover frequency (or bandwidth) remains within the acceptable range, which is about 1 rad/s.

show abstract

Section: Neural Network-based Wind Speed Estimationmentioning

confidence: 99%

Section: Neural Network-based Wind Speed Estimationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Predictive Control of a Wind Turbine Based on Neural Network-Based Wind Speed Estimation

2023

View full text Add to dashboard Cite

show abstract

“…En el control de sistemas dinámicos, las redes neuronales artificiales se utilizan para modelar sistemas complejos que no se pueden modelar fácilmente mediante técnicas algorítmicas convencionales (Tiumentsev & Egorchev, 2019). Las redes neuronales artificiales se utilizan para aprender el comportamiento del sistema y posteriormente controlarlo en tiempo real.…”

Section: Introductionunclassified

Diseño y Control de Sistemas Mecatrónicos

Gudiño-Lau

2023

View full text Add to dashboard Cite

La Ingeniería en Mecatrónica es un área multidisciplinaria que involucra a las ingenierías mecánica, eléctrica, computación y control automático; actualmente los estudiantes, profesores, investigadores y el sector productivo se suman a la innovación de nuevos proyectos, a procesos inteligentes, al desarrollo de prototipos y a la creación de nuevas tecnologías con la finalidad de apoyar al ser humano

show abstract

Semiempirical Neural Network Models of Controlled Dynamical Systems

Cited by 2 publications

References 28 publications

Predictive Control of a Wind Turbine Based on Neural Network-Based Wind Speed Estimation

Predictive Control of a Wind Turbine Based on Neural Network-Based Wind Speed Estimation

Diseño y Control de Sistemas Mecatrónicos

Contact Info

Product

Resources

About